Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8693
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal proceedings and judicial oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marvelous
    -0.74
    thank
    -0.68
     FANTASY
    -0.67
     Started
    -0.66
     delightful
    -0.65
     Turns
    -0.64
     Unleashed
    -0.63
     Rhythm
    -0.63
     amazing
    -0.62
     Awesome
    -0.62
    POSITIVE LOGITS
     lawfully
    0.99
     revocation
    0.95
     duly
    0.95
     treaties
    0.95
     judicial
    0.94
     infring
    0.92
     veto
    0.92
     judiciary
    0.91
     authorised
    0.90
     constitutional
    0.89
    Activations Density 1.112%

    No Known Activations